NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use
5 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
NVIDIA Nemotron 3.5 Super reasoning model (120B total, 12B active) served with text-only input
1 provider
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
13 providers
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
17 providers
Open Nemotron omni model combining reasoning with text, vision, and audio
6 providers
Nemotron model for efficient reasoning, coding, and specialized AI agents
1 provider
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
17 providers
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
14 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Nemotron 3.5 Super VL 120B A12Bnvidia/nemotron-3.5-super-vl-120b-a12b | NVIDIA |
1.04858M | $0.08 | $0.45 | 2026-10-15 | ||
| Nemotron 3.5 Super 120B A12Bnvidia/nemotron-3.5-super-120b-a12b | NVIDIA |
1.04858M | $0.2 | $0.5 | 2026-10-15 | ||
| Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning | NVIDIA |
262.144K | $0.025 | $0.12 | 2026-08-11 | ||
| Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b | NVIDIA |
1M | $0.1 | $0.1 | 2026-06-04 | ||
| Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/nemotron-3-nano-omni-30b-a3b-reasoning | NVIDIA |
256K | $0.1 | $0.25 | 2026-04-28 | ||
| Nemotron Cascade 2 30B A3Bnvidia/nemotron-cascade-2-30b-a3b | NVIDIA |
256K | — | — | 2026-03-19 | ||
| Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b | NVIDIA |
262.144K | $0.05 | $0.25 | 2026-03-11 | ||
| Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | NVIDIA |
262.144K | $0.05 | $0.2 | 2025-12-15 |